Borrowing it
Nothing to install: this file belongs to pedroknigge/Open-Neural-Substrate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pedroknigge/Open-Neural-Substrate/main/CLAUDE.mdgit clone --depth 1 https://github.com/pedroknigge/Open-Neural-SubstrateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/pedroknigge/open-neural-substrate/claude-md)<a href="https://agentmods.dev/instructions/pedroknigge/open-neural-substrate/claude-md"><img src="https://agentmods.dev/badge/instructions/pedroknigge/open-neural-substrate/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/pedroknigge/open-neural-substrate/claude-md"><img src="https://agentmods.dev/badge/instructions/pedroknigge/open-neural-substrate/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02228 | $0.02228 |
| Opus 5 | $0.01114 | $0.01114 |
| Sonnet 5 | $0.00446 | $0.00446 |
| Haiku 4.5 | $0.00223 | $0.00223 |
Grade A, and why
Open-Neural-Substrate CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Instructions for Claude Code
What This Project Is
Open Neural Substrate (ONS) — a persistent local knowledge service that acts as a second brain. It stores information as "neurons" (structured JSON records with Markdown content, embedding vectors, and weighted connections). Any software — Claude, Codex, GPT, scripts, automations — queries and updates it via a local API on port 52830.
This is NOT a notes app. It is a living knowledge graph with adaptive connections and background consolidation (like biological sleep).
Architecture Summary
- Database: SQLite + sqlite-vec extension. Three tables:
neurons,edges,embeddings. - Server: FastAPI on
localhost:52830. Four core endpoints:/query,/upsert,/rewire,/delete/{id}. - Integrations: MCP server wrapper for Claude, OpenAI-compatible tool schema for GPT/Codex, plain HTTP for everything else.
- Consolidation: Background process that runs during idle (30min no activity). Four passes: replay/strengthen, cluster/propose, decay/prune, re-embed stale.
- Embedder: Pluggable. Default: local sentence-transformers model. Fallback: OpenAI/Anthropic API.
- Persistence: Runs as systemd user service (Linux), LaunchAgent (macOS). Starts at login, always available.
Key Design Rules
- Neurons are the atomic unit. Every piece of knowledge is one neuron. No separate tables for customers vs tasks vs notes — they're all neurons with a
typefield. - Edges are first-class. Connections live in their own table, NOT embedded in neuron JSON. A neuron can have thousands of connections without bloating its own record.
- Embeddings are model-agnostic. Stored per-model in a separate table. When a new model queries, embed on demand and cache. No lock-in.
- All writes are local. Editing one neuron never cascades. No global reindexing on single edits.
- Soft deletes only.
deletedflag + version history. Nothing is permanently lost. - LLM writes require guardrails. LLM-proposed changes are logged with
created_by: "llm"and can require human approval. - Consolidation is separate. The sleep cycle is a distinct module that reads interaction logs and proposes changes.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 172 lines · 2,228 tokens per session scan A 1896c957c94c
Open-Neural-Substrate CLAUDE.md is an instructions file published in the GitHub repository pedroknigge/Open-Neural-Substrate (0 stars, last pushed 5mo ago), licensed MIT. It adds 2,228 tokens to every session, about $0.0111 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.